I am interested in 3D computer vision, including correspondences between images,
camera pose estimation, 3D reconstrucrion, visual localization and SLAM.
TL;DR:
We propose the first framework to learn a single generalizable image matching model from internet videos.
Application / Influence:DJI Automotive
TL;DR:
We found that the keypoint score has little effect on the matching performance of SuperGlue, and proposed finding the correspondence between foreground and background in image matching.
Application / Influence:LightGlue
TL;DR:
We have applied receptive field constraints in detecting and describing keypoints, and proposed a neighbor ambiguity mask.
Application / Influence:Video Stabilization